Liang He

18

Papers

104

Total Citations

Papers (18)

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning

CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering

Human Simulacra: Benchmarking the Personification of Large Language Models

A Hierarchical Network for Multimodal Document-Level Relation Extraction

MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models

BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind

Generative Calibration of Inaccurate Annotation for Label Distribution Learning

Shifting More Attention to Visual Backbone: Query-Modulated Refinement Networks for End-to-End Visual Grounding

LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion

DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection

MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA

AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning

Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning

Aspect Enhancement and Text Simplification in Multimodal Aspect-Based Sentiment Analysis for Multi-Aspect and Multi-Sentiment Scenarios

Disentangled Modeling of Preferences and Social Influence for Group Recommendation

Co-evolution Transformer for Protein Contact Prediction